Know a great AI tool or AI news source? Submit it to AiByts
AiByts
Sign inGet started

Backgrind Blog

Stay updated with the latest developments in Artificial Intelligence

v0.7.0

LLM inference in C/C++. Contribute to ggml-org/llama.cpp development by creating an account on GitHub.

llama.cpp11 min read

b11669

llama.cpp1 min read

Latest AI News

  • OpenAI open-sourced the Codex harness: what you actually got

    OpenAI just made the engine under Codex an Apache-2.0 platform — codex exec, the SDK, and the JSON-RPC app-server. The pitch is one number: harness changes alone took the same model from 13.3% to 38.3% on ARC-AGI-3 with 6x fewer tokens.

    Backgrind Blog10 min read

  • Ox Alpha: who is behind OpenRouter's free mystery model?

    A nameless model with a 1M-token context dropped on OpenRouter and OpenCode, free for a week, and nobody has claimed it. The forensic trail — a leaked Java stack trace, error code 1214, 30/30 tokenizer matches — points hard at Zhipu’s next GLM.

    Backgrind Blog10 min read

  • Meta Muse Code: install, pricing, and how it compares to Claude Code

    Meta's first terminal coding agent launched with a benchmark chart it loses — and a design worth stealing: background agents that persist all session, sub-agents fanned into isolated git worktrees, and a 12–21x discount if you let Meta train on your code.

    Backgrind Blog10 min read

  • Measuring whether a coding agent is actually helping

    The three metrics every team reaches for first — lines written, acceptance rate, self-reported time saved — are the three that reward an agent producing more code than you needed.

    Backgrind Blog20 min read

  • Which config file actually wins?

    Your personal setting is being ignored, or the repo's is — and the reason is that the direction of precedence is not the same for every mechanism. settings.json lets the repo beat your laptop; skills let your laptop beat the repo; CLAUDE.md lets nothing beat anything; permission rules refuse to…

    Backgrind Blog19 min read

  • Hooks in the Claude Agent SDK: every event, measured

    The programmatic hooks you pass in options.hooks, not the shell hooks in settings.json — and the difference matters, because by default both fire in the same run. We registered a callback on all 31 events and ran it until we had the thing nobody publishes: the measured firing order.

    Backgrind Blog19 min read

  • Running a coding agent in CI: the walls, in the order you hit them

    The agent gets one shot, on a machine with no browser and nobody to ask — which changes which failures you get. We ran four headless arms on one real failing test: the locked-down run with no allowlist was denied Bash and Edit, wrote nothing, exited 0, reported subtype "success" and cost $0.383 —…

    Backgrind Blog21 min read

  • Letting an agent write your tests

    The one job everyone hands an agent first, and the one place a wrong answer looks exactly like a right one. We gave Claude Code the same 7-line function twice — once with the implementation, once with only a spec — then broke the code nine ways to see which suite noticed.

    Backgrind Blog15 min read

  • Running a coding agent inside a container

    The thing people reach for the moment they want to stop approving every command — and the one fear it does not remove. A real Dockerfile, a default-deny egress firewall measured before and after, and the four things that break first: a build-arg token that shows up in docker history three times…

    Backgrind Blog20 min read

  • Migrating a large codebase with an agent

    A migration is not one task, it is a thousand nearly identical ones — and that changes how you drive it. The pilot-then-rules-then-batches shape, and the part everyone skips: a codemod beats the agent on the mechanical 80%.

    Backgrind Blog16 min read

  • Managing context in a long Claude Code session

    The window is the constraint everything else follows from, and file reads are what fill it — about 31% of a representative session, against 1% for your own prompts. What /compact and /clear each do, and the part nobody warns you about: compaction does not bring everything back.

    Backgrind Blog17 min read

  • Gemini CLI: install, configure, and where it fits

    Google's terminal agent is the only one of the three with a free tier that works without a card — 1,000 model requests a day on a plain Google sign-in. The three auth paths and what each actually meters, why GEMINI.md silently ignores your AGENTS.md, the nested settings.json shape, MCP and…

    Backgrind Blog16 min read

  • What an AI coding agent actually costs — and how to spend less

    The subscription-vs-API crossover is a computable number, not a matter of taste — and the tokens go almost nowhere people assume. We run a 40-turn Opus 5 session at $13.20 uncached and $2.86 warm, work the break-even for Pro, Max 5x and Max 20x, price the same session across four models at a clean…

    Backgrind Blog19 min read

  • Codex CLI notifications: how the notify hook actually works

    The notify hook has exactly one event, hands you the payload as an argv argument rather than on stdin, and can never block a tool call. The verified payload shape, a runnable script, per-run vs global wiring, and when to reach for lifecycle hooks instead.

    Backgrind Blog11 min read

Showing 18 of 30 stories

Load more stories
AiByts Weekly Brief

Get the top AI news and tools straight to your inbox every week.

Weekly · AI news from Backgrind Blog

Join 15,000+ AI enthusiasts